5 tagged llm-gateway, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available. Runs locally from the freellmpool Python package.
MCP server Claude CodeCodexCursor +2
MCP server "unified-ai-system" as configured in happy520ai/unified-ai-system. Runs in Docker (ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0).
MCP server Claude CodeCodexCursor +2
Self-hosted, OpenAI- and Anthropic-compatible LLM gateway that turns every request into a payload-free, attributable cost receipt -- know what your AI work costs, without keeping what it said. Runs locally from the inferrail Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Pay-per-call agent tools via x402 (USDC on Base): chat, prices, funding, RNG. No account or keys. Remote server at x402.shizu.me.
hedging8563/tokenlab-mcp-server
MCP server Claude CodeCodexCursor +2
OpenAPI-generated TokenLab MCP server for models, native AI, multimodal media, tasks, and files. Runs locally from the @tokenlabai/mcp-server npm package. Needs 7 environment variables to run.